test

app.py

@@ -1,154 +1,81 @@
 import gradio as gr
+from PIL import Image, ImageDraw
 import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
-import torch
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
-
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
-
-    return image, seed
-
-
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
-
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 640px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
-
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
-
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
+
+# 定义全局变量保存 masks
+masks = []
+
+# 颜色列表
+colors = [(255,0,0), (0,255,0), (0,0,255), (255,255,0), (255,0,255), (0,255,255)]
+
+def add_mask(img_dict, color_idx):
+    color_idx = int(color_idx)
+    mask = img_dict['mask']
+    orig_img = img_dict['image']
+
+    if orig_img.ndim == 2:
+        orig_img = np.stack([orig_img]*3, axis=-1)
+    if orig_img.dtype != np.uint8:
+        orig_img = orig_img.astype(np.uint8)
+
+    img_pil = Image.fromarray(orig_img)
+    mask_pil = Image.fromarray(mask).convert("L")
+
+    mask_np = np.array(mask_pil)
+    color = colors[color_idx % len(colors)]
+
+    # 创建 RGBA 彩色 mask
+    colored_mask_np = np.zeros((mask_np.shape[0], mask_np.shape[1], 4), dtype=np.uint8)
+    mask_bool = mask_np > 0
+    for c in range(3):
+        colored_mask_np[..., c][mask_bool] = color[c]
+    colored_mask_np[..., 3][mask_bool] = 100
+
+    colored_mask = Image.fromarray(colored_mask_np, mode="RGBA")
+
+    base = Image.alpha_composite(img_pil.convert("RGBA"), colored_mask)
+
+    # 👇 关键修改：返回一张“空白”的 mask 而不是 None
+    empty_mask = np.zeros_like(mask)
+
+    return base, orig_img
+
+
+def reset_masks():
+    global masks
+    masks = []
+    return None
+
+# 写一个单纯的赋值函数
+def assign_value(src):
+    return src
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        # image_input = gr.Image(type="pil", label="上传图片")
+        mask_canvas = gr.Image(type="numpy", tool="sketch", interactive=True, label="在上面画 mask")
+    
+    color_index = gr.Number(value=0, label="当前颜色索引 (自动循环)")
+    
+    add_btn = gr.Button("添加当前 mask")
+    reset_btn = gr.Button("清空所有 mask")
+    
+    output = gr.Image(type="pil", label="叠加后的 mask 结果")
+    # orig_img = 0
+    add_btn.click(
+        add_mask, 
+        inputs=[mask_canvas, color_index], 
+        outputs=[output, mask_canvas]
+    ).then(
+        lambda idx: (idx + 1) % len(colors), 
+        inputs=color_index, 
+        outputs=color_index
+    ).then(
+        lambda _: None,  # 清空 mask_canvas
+        inputs=None,
+        outputs=mask_canvas
     )
 
-if __name__ == "__main__":
-    demo.launch()
+    reset_btn.click(reset_masks, outputs=output)
+    
+demo.launch()